© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6097
    Prev
    Next
    INDEX
    Explanations

    instances of the word "viewing" and similar forms related to observation or perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.69
     hear
    -0.62
    GOTREF
    -0.60
     Efq
    -0.57
    addPreferredGap
    -0.57
     iNdEx
    -0.56
    bootstrapcdn
    -0.56
     NSCoder
    -0.56
    OCCURRED
    -0.56
    hear
    -0.56
    POSITIVE LOGITS
     viewing
    1.59
     Viewing
    1.51
    Viewing
    1.41
    viewing
    1.32
     listening
    1.23
     Listening
    1.12
    Listening
    1.09
     watching
    1.03
    listening
    1.03
    Watching
    0.99
    Activations Density 0.094%

    No Known Activations